Using Gaussian processes for variance reduction in policy gradient algorithms
From MaRDI portal
Recommendations
- Variance reduction techniques for gradient estimates in reinforcement learning
- Parametric Approximation Policy Iteration Algorithm Based on Gaussian Process
- Exploiting Variance Reduction Potential in Local Gaussian Process Search
- Approximate gradient methods in policy-space optimization of Markov reward processes
Cited in
(6)- Variance reduction techniques for gradient estimates in reinforcement learning
- Analysis and improvement of policy gradient estimation
- Exploiting Variance Reduction Potential in Local Gaussian Process Search
- Parametric Approximation Policy Iteration Algorithm Based on Gaussian Process
- Hessian matrix distribution for Bayesian policy gradient reinforcement learning
- Variational policy search using sparse Gaussian process priors for learning multimodal optimal actions
This page was built for publication: Using Gaussian processes for variance reduction in policy gradient algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2908998)
